LogoLogo
  • GETTING STARTED
    • Welcome to the NLX platform
    • How NLX works
    • Guides
      • Analytics dashboard
      • Chat
      • Generative Journey (Slots)
      • Model Context Protocol
      • Voice
      • Voice+ script
      • Touchpoint components
        • Carousel modality
        • Video modality
    • Terms & concepts
    • Generative AI
    • Developer
  • Build
    • Workspace setup
    • Flows
      • Intro to flows & variables
      • The Canvas
      • Flow settings
      • Nodes
      • Flow appearance
    • Resources
      • Actions
        • Implementation
        • Request model
      • Analytics tags
      • Context variables
      • Data requests
        • Implementation
        • Response model
        • Request model
      • Knowledge bases
        • Ingest content
        • Add metadata (beta)
        • Apply KB
      • Lifecycle hooks
        • Implementation
      • Modalities
      • Secrets
      • Slots (custom)
        • Adding values
        • Translating slots
      • Voice+ scripts
        • Add + download script
        • Deploy script + install SDK
        • Create Voice+ flow
    • Integrations
      • Channels
        • Alexa
        • Amazon Chime SDK
        • Amazon Connect
        • AWS End User Messaging SMS
        • AWS End User Messaging Social
        • Bandwidth
        • Genesys
        • Twilio
        • Zendesk Sunshine
      • LLM services
        • Amazon Bedrock
        • Anthropic
        • Azure OpenAI
        • Cerebras
        • Cohere
        • Google Vertex AI
        • Groq
        • NVIDIA
        • OpenAI
        • xAI
      • NLP
        • Amazon Lex
        • Google Dialogflow
        • Google Dialogflow CX
        • Custom NLP
    • Translations
  • Deploy & test
    • Applications
      • Attach flows
      • Assign default behavior
      • Add channels
        • API
          • REST API
        • Alexa
        • Amazon Chime SDK
        • Amazon Connect
        • AWS End User Messaging SMS
        • AWS End User Messaging Social
        • Genesys
        • Genesys SMS
        • Messenger
        • Microsoft Teams
        • Slack
        • SMS via Bandwidth
        • Twilio SMS
        • Twilio Voice
        • WhatsApp via Twilio
        • Zendesk Sunshine
      • Deploy
      • Optional: Set lifecycle
      • Optional: Set languages
    • Test
      • Test a conversation
      • Automated tests
      • Test an external integration
  • Analyze
    • Conversations
    • Analytics
      • Creating dashboards
      • Formulas & multi-metrics
      • Canvas analytics
    • Training
  • Workspace Settings
    • Escalation channels
    • Resource tags
    • Audit
  • Admin
    • Access control
      • Roles & permissions
    • Notifications
    • FAQ
    • Contact support
Powered by GitBook
On this page
  • What are Automated tests?
  • AI tests (intent recognition)
  • Execute test
  • Automated test Settings
  • Conversation flow test
  1. Deploy & test
  2. Test

Automated tests

Set up and quickly test inputs or training data using Automated tests in NLX

Last updated 13 days ago

An application build is required before any Automated test may be used. See .

What are Automated tests?

Automated tests allow you to easily test your application's performance with recognizing user intent and matching to the correct flow (based on your provided descriptions or training phrases), or they allow you to quickly execute saved conversation inputs when running frequent tests with your conversation workflows.


AI tests (intent recognition)

To test your application's ability to recognize user intent and invoke the appropriate flow from provided training phrases, create an AI test on your application:

  • Click Automated tests tab of your application > Under AI tests section, select Create test

  • Enter a test name > Click Save

  • Select + Add test

  • Select Generate to ingest training data of a flow(s)*

    • Alternatively, you may skip this option and manually enter an utterance(s) to test

  • Review or specify the flows you want to test each utterance against

  • Select Save

*If your flow's training data includes custom , the Generate combinations toggle ensures all variations of those slot values are simulated in the test.

Once satisfied and ready to run your test, select the Test executions tab to process your test.

Execute test

To execute a saved intent recognition test, select the test:

  • Choose Test executions tab > Click Execute test

  • Once the test completes its run, you may select it to view detailed results

Failed phrases display the expected flow to be matched alongside the actual matched flow:


Automated test Settings

Manage custom settings for all AI intent recognition tests created and executed for your application. Select or create an AI test saved on your application, and choose the test's Settings tab:

  • Failure threshold: Indicates the percentage of tests allowed to fail in the whole test suite before a build fails

  • Minimum confidence score: Minimum confidence score indicates the NLP confidence value each test must achieve before it fails. This applies to every individual test

To delete an automated flow recognition test, select the Delete application test option under Danger zone.


Conversation flow test

To create an automated conversation flow test, begin by entering Test mode on a flow:

  • Select a flow

  • Provide inputs in the test panel to converse with your application

  • Enter a test name

  • Click Save

Your named automated flow test will now be visible to replay. You may proceed from the point of the save and continue testing the conversation or generate additional automated tests.

Execute during build: Automatically triggers your test after each new successful

Toggle mode to Test on the bottom of

To save your sequence of inputs, select the play button icon > Choose + New automated test

All saved automated flow tests will be visible from the test panel in the flow or from an application's Automated tests tab where .

▶️
your Canvas builder
the flow is attached
✨
Deploy
Slots
build